HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters

TL;DR

HunyuanVideo-Avatar is a multimodal diffusion transformer model that generates high-fidelity, emotion-controllable, multi-character dialogue videos with improved consistency and realism, addressing key challenges in audio-driven human animation.

Contribution

It introduces three innovations: a character image injection module, an emotion transfer module, and a face-aware audio adapter, enabling dynamic, emotion-aligned, multi-character video generation.

Findings

Surpasses state-of-the-art on benchmark datasets

Generates realistic, emotion-aligned multi-character videos

Effective in dynamic and immersive scenarios

Abstract

Recent years have witnessed significant progress in audio-driven human animation. However, critical challenges remain in (i) generating highly dynamic videos while preserving character consistency, (ii) achieving precise emotion alignment between characters and audio, and (iii) enabling multi-character audio-driven animation. To address these challenges, we propose HunyuanVideo-Avatar, a multimodal diffusion transformer (MM-DiT)-based model capable of simultaneously generating dynamic, emotion-controllable, and multi-character dialogue videos. Concretely, HunyuanVideo-Avatar introduces three key innovations: (i) A character image injection module is designed to replace the conventional addition-based character conditioning scheme, eliminating the inherent condition mismatch between training and inference. This ensures the dynamic motion and strong character consistency; (ii) An Audio Emotion Module (AEM) is introduced to extract and transfer the emotional cues from an emotion reference image to the target generated video, enabling fine-grained and accurate emotion style control; (iii) A Face-Aware Audio Adapter (FAA) is proposed to isolate the audio-driven character with latent-level face mask, enabling independent audio injection via cross-attention for multi-character scenarios. These innovations empower HunyuanVideo-Avatar to surpass state-of-the-art methods on benchmark datasets and a newly proposed wild dataset, generating realistic avatars in dynamic, immersive scenarios.